> ## Documentation Index
> Fetch the complete documentation index at: https://docs.statebase.org/llms.txt
> Use this file to discover all available pages before exploring further.

# When to Checkpoint

> Optimizing for reliability vs. token costs.

Checkpointing is the act of committing your agent's state and interaction history to StateBase. Doing it too often is noisy; doing it too rarely is dangerous.

## The "Critical Path" Principle

You should create a checkpoint (add a turn or update state) whenever the agent makes a **commitment**.

### ✅ Do Checkpoint:

* **After Tool Execution**: If the agent successfully calls a database or API, save that result immediately.
* **Before User Confirmation**: Save the proposed action state so if the user says "No," you can revert to the decision point.
* **After Memory Extraction**: When the agent learns something permanent, commit it to long-term memory.
* **Every X Turns**: For long conversations, a "heartbeat" checkpoint every 5 turns ensures a crash doesn't lose everything.

### ❌ Don't Checkpoint:

* **Interim Reasoning**: If the agent is "thinking" internally across multiple LLM calls for a single task, only save the final outcome.
* **Greeting/Small Talk**: Don't waste storage on "Hello" unless it contains identity data.

## Cost vs. Safety Tradeoffs

Every checkpoint in StateBase is optimized for millisecond latency, but it does incur a storage record.

| Frequency         | Target Use Case         | Founder Takeaway                           |
| :---------------- | :---------------------- | :----------------------------------------- |
| **Per-Turn**      | Financial/Health Agents | Infinite safety, slightly higher latency.  |
| **Per-Milestone** | Creative/Writing Agents | Cheaper, but rollbacks are less granular.  |
| **Manual**        | Developer Experiments   | Complete control, higher logic complexity. |

**Recommendation**: Start with **Per-Turn** checkpointing. You can always optimize later, but you can't restore what was never saved.